Okay. That doesn't make anything I said untrue.

Though I wouldn't say that ChatGPT is "literally everywhere", it certainly isn't limited to "tech weirdos". Plenty of non-tech people are using it for work and school, or are simply aware of it from the extensive news coverage or TikToks.

"But that is also beside the point, there was an improvement while the sessions lasted."

Really? That seems like the most important factor of "self-improvement". If it only improved its error in the session but makes the same error if you refresh the page, then it didn't improve itself, it simply improved its output. There's a huge difference between permanently upgrading your own capabilities from external input, and simply fixing text already written on the page with external input.

(Also, it sometimes continues to make the same error within the same session even after pointing out its mistake, which is greater evidence against true self-improvement.)

AI has been generating images that customers would use (and are using) rather than images created by humans. That's what matters when we're talking about job replacement. Whether said images are "art" is irrelevant.